JMIR Publications

ABSTRACT

Background:

Currently, assessment for mental health is done by experts using interview techniques, questionnaires, and test batteries, and following standardized manuals; however, there would be myriad benefits if behavioural correlates could predict mental health and be used for population screening or prevalence estimations. A variety of digital sources of data (e.g., online search data, social media posts) have been previously proposed as candidates for digital phenotyping—the digital quantification of disease phenotypes—in the context of mental health. Playing games on computers, gaming consoles, or mobile devices (i.e., digital gaming) has become a leading leisure activity of choice and yields rich data from a variety of sources.

Objective:

In this paper, we argue that game-based data from commercial off-the-shelf games have potential to be used as a digital biomarker to assess and model mental health and health decline. Although there is great potential in games developed specifically for mental health assessment (e.g., Sea Hero Quest), we focus on data gathered “in-the-wild” from playing commercial off-the-shelf games designed primarily for entertainment.

Methods:

In this paper, we argue that the behavioural traces left behind by natural interactions with digital games can be modeled using computational approaches for big data. To support our argument, we present an investigation of existing data sources, a categorization of observable traits from game data, and examples of potentially useful digital biomarkers.

Results:

Our investigation reveals different types of data that are generated from play, and the sources from which these data can be accessed. Based on these insights, we describe five categories of digital biomarkers that can be derived from game-based data, including: behaviour, cognitive performance, motor performance, social behaviour, and affect. For each type of biomarker, we describe the data type, the game-based sources from which it can be derived, its importance for mental health modeling, and any existing statistical associations with mental health that have been demonstrated in prior work. We close with a discussion on the limitations and potential of data from commercial off-the-shelf games for use as a digital biomarker of mental health.

Conclusions:

When people play commercial digital games, they produce significant volumes of high-resolution data—data that is not just related to play frequency, but that includes performance data reflecting low-level cognitive and motor processing, text-based data that is indicative of affective state, social data that reveals networks of relationships, content choice data that implies preferred genres, and contextual data that divulges where, when, and with whom they are playing. These data provide a source for quantification of disease phenotypes of mental health. Produced by engaged human behaviour, game data have potential to be leveraged for population screening or prevalence estimations, leading toward at-scale, non-intrusive assessment of mental health.